© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 30122
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    This neuron does not respond to any tokens—that is, it remains inactive and does not detect any pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Here
    -0.06
    /r
    -0.06
    Forward
    -0.06
     nella
    -0.06
    婚
    -0.06
    .brand
    -0.06
    298
    -0.06
    /--
    -0.06
     větš
    -0.06
    농
    -0.06
    POSITIVE LOGITS
     плит
    0.07
    PCP
    0.07
     bilg
    0.07
    eless
    0.06
    zap
    0.06
     والم
    0.06
     mực
    0.06
     hồng
    0.06
     Einsatz
    0.06
     ROUT
    0.06
    Activations Density 0.028%

    No Known Activations